Functionality for AI

Functionality that supports deep learning workflow for wireless applications

You can use Deep Learning Toolbox™ functionality in wireless communications systems that contain neural networks. Use of functions in a neural network during training requires dlarray (Deep Learning Toolbox) support. For the set of wireless communications domain-specific functions that support dlarray (Deep Learning Toolbox) objects, see Wireless Communications (Deep Learning Toolbox).

Functions

expand all

dlarray Support

`awgn`	Add white Gaussian noise to signal
`bit2int`	Convert bits to integers (Since R2021b)
`genqammod`	General quadrature amplitude modulation (QAM)
`ofdmmod`	Modulate using OFDM method
`ofdmdemod`	Demodulate using OFDM method
`ofdmChannelResponse`	Calculate OFDM channel response (Since R2023a)
`ofdmEqualize`	Equalize OFDM signals (Since R2022b)

Objects

expand all

dlarray Support

`comm.ChannelFilter`	Filter signal using multipath gains at specified path delays
`comm.MIMOChannel`	Filter input signal through MIMO multipath fading channel

Data Import and Preprocessing

`dpdPreprocessor`	Digital predistortion (DPD) data input preprocessor for AI algorithms (Since R2024b)
`signalDatastore`	Datastore for collection of signals

Topics

Cosine Similarity As a Channel Estimate Quality Metric
Use the cosine similarity metric to compare two vectors. (Since R2024b)
Normalized Mean Squared Error as a Distance Measure
Use the normalized mean squared error (NMSE) as a loss function for training a neural network in a wireless communications application. (Since R2025a)

Related Information

Prerequisites for Deep Learning with MATLAB Coder (MATLAB Coder)
Domain-Specific Functions with dlarray Support (Deep Learning Toolbox)
Datastores for Deep Learning (Deep Learning Toolbox)